Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to boasting or pride

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "boast" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stranded
    -0.75
    ondo
    -0.74
    uters
    -0.73
     inhal
    -0.66
    relation
    -0.66
    early
    -0.65
    ocol
    -0.64
    uter
    -0.64
     oxygen
    -0.63
     isot
    -0.63
    POSITIVE LOGITS
     boasted
    1.27
     boasting
    1.23
     boasts
    1.20
     boast
    1.10
     bragging
    0.97
    indal
    0.90
    rets
    0.86
     4090
    0.83
    ries
    0.80
    iveness
    0.78
    Act Density 0.005%

    No Known Activations